GeneMask: Fast Pretraining of Gene Sequences to Enable Few-Shot Learning

Abstract

Large-scale language models such as DNABert and LOGO aim to learn optimal gene representations and are trained on the entire Human Reference Genome. However, standard tokenization schemes involve a simple sliding window of tokens like k-mers that do not leverage any gene-based semantics and thus may lead to (trivial) masking of easily predictable sequences and subsequently inefficient Masked Language Modeling (MLM) training. Therefore, we propose a novel masking algorithm, GeneMask, for MLM training of gene sequences, where we randomly identify positions in a gene sequence as mask centers and locally select the span around the mask center with the highest Normalized Pointwise Mutual Information (NPMI) to mask. We observe that in the absence of human-understandable semantics in the genomics domain (in contrast, semantic units like words and phrases are inherently available in NLP), GeneMask-based models substantially outperform the SOTA models (DNABert and LOGO) over four benchmark gene sequence classification datasets in five few-shot settings (10 to 1000-shot). More significantly, the GeneMask-based DNABert model is trained for less than one-tenth of the number of epochs of the original SOTA model. We also observe a strong correlation between top-ranked PMI tokens and conserved DNA sequence motifs, which may indicate the incorporation of latent genomic information. The codes (including trained models) and datasets are made publicly available at https://github.com/roysoumya/GeneMask.

12 pages including appendix. Accepted for publication at 26th European Conference on Artificial Intelligence ECAI 2023

References in corpus (8)

• ERNIE: Enhanced Representation through Knowledge Integration
• On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima
• dna2vec: Consistent vector representations of variable-length k-mers
• Fine-Grained Zero-Shot Learning with DNA as Side Information
• PMI-Masking: Principled masking of correlated spans
• Multi-modal Self-supervised Pre-training for Regulatory Genome Across Cell Types
• InforMask: Unsupervised Informative Masking for Language Model Pretraining
• Learning Better Masking for Better Language Model Pre-training

Cited by in corpus (1)

• Unlocking Efficiency: Adaptive Masking for Gene Transformer Models